Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

68136203271 · Jun 202019922001200920182026
48 results for weight fine-tuning

Optimizes sparse fine-tuning for privacy in neural networks.

problem Performance gap between DP-SGD and non-private fine-tuning.
method Optimization-based approach using private gradient information for selecting trainable weights.
result Our selection method leads to better prediction accuracy compared to existing approaches.

Weight Squeezing transfers knowledge from large models to smaller ones, improving performance and speed.

problem Transfer learning and model compression for faster and more efficient training.
method Reparameterization of weights from a large model to a smaller one.
result Weight Squeezing outperforms other methods on GLUE benchmark with faster training.

A new method constrains deep networks during fine-tuning to improve generalization.

problem Improving generalization of fine-tuned deep networks.
method A neural network generalisation bound based on distance from initial weights constrains the hypothesis class to a small sphere.
result Empirical evaluation shows superior generalization performance compared to existing methods.

Researchers develop method to protect against 'weight poisoning' attacks on pre-trained models.

problem The security threat of downloading untrusted pre-trained weights that can be manipulated after fine-tuning.
method RIPPLe regularization method and Embedding Surgery initialization procedure.
result Demonstrated that weight poisoning attacks are possible even with limited knowledge of the dataset and fine-tuning procedure.

LoRA fine-tuning explained with gradient dynamics for low-rank perturbations.

problem Understanding why gradient descent converges to useful low-rank perturbations in LoRA fine-tuning.
method Generalized student-teacher setting with i.i.d. samples and online gradient descent.
result Gradient descent converges to the teacher model in dkO(1)dk^{O(1)} iterations under certain conditions.

EVA adapts LoRA for faster, more efficient fine-tuning.

problem Fast and efficient fine-tuning of large models for specific tasks.
method EVA uses directions capturing most activation variance for initialization, maximizing gradient signal and reducing parameters.
result EVA achieves faster convergence and higher average scores across tasks, reducing parameters.

Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.

problem Improving neural network performance through adaptive pruning of weights.
method Optimizes stochastic pruning masks by minimizing expected loss, considering data-adaptive regularization and feature alignment.
result Probabilistic fine-tuning leads to improved test error over baseline methods in neural networks.

This tutorial reviews RL-based methods for optimizing diffusion models to maximize specific metrics.

problem Optimizing diffusion models to generate samples that maximize specific metrics in practical applications.
method Various RL algorithms including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
result Exploration of strengths and limitations of RL-based fine-tuning algorithms and their benefits compared to non-RL-based approaches.

Proposes a new RL method to fine-tune flow-based models with arbitrary rewards.

problem Challenges in fine-tuning continuous flow-based generative models with arbitrary reward functions.
method Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regularization (ORW-CFM-W2)
result Achieves optimal policy convergence with controllable trade-offs between reward maximization and diversity preservation.

Paper compresses neural network weight-updates for image artifacts removal.

problem Efficiently compressing neural network weight-updates for image artifacts removal.
method Fine-tuning a pre-trained artifact removal network on target data with a compression objective that encourages sparse and quantized weight-updates.
result Achieves reconstruction quality comparable to traditional codecs at comparable bitrates.

A new meta-learning framework that assigns weights to source tasks based on target samples.

problem Learning initialization for target tasks with limited labeled examples.
method A general framework that assigns weights to the loss of different source tasks, which can depend on the target samples. Provides upper bounds and develops a learning algorithm based on minimizing the error bound with respect to an empirical IPM.
result Empirically, the weighted meta-learning algorithm finds better initializations than uniformly-weighted meta-learning algorithms.

DTM improves dLLM fine-tuning stability and performance.

problem Intractable sequence-level marginal likelihoods for masked diffusion models.
method Discrete Tilt Matching (DTM) recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting.
result DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.

Fine-tuning neural networks to guarantee performance on specific examples can also introduce incorrect inputs.

problem Ensuring reliable performance of neural networks on specific examples.
method Using SMT solvers to fine-tune ReLU neural networks to guarantee outcomes on a finite set of particular examples.
result Fine-tuning can introduce incorrect inputs that trigger unexpected performance.

Optimizer memory affects learning rate sensitivity in shuffle order, impacting fine-tuning noise.

problem Optimizer memory affects the learning rate sensitivity in shuffle order, leading to fine-tuning noise.
method Isolated the mechanism of fixed-clock optimizer memory affecting the learning rate sensitivity in shuffle order, deriving a fit-free way to size the noise.
result Fixed-clock optimizers like AdamW produce a larger first-order noise channel compared to memoryless optimizers, affecting fine-tuning comparisons.

New method adapts neural networks without losing prior knowledge.

problem Understanding and enabling flexible adaptation of neural networks.
method Differential geometry framework, functionally invariant paths (FIP).
result Achieves comparable state-of-the-art performance on continual learning and sparsification tasks.

InfoSFT improves LLMs by focusing on informative, medium-confidence tokens.

problem Overfitting to unlikely samples and degradation of prior capabilities in SFT.
method InfoSFT uses a principled weighting scheme to concentrate learning signals on medium-confidence tokens.
result InfoSFT improves generalization and preserves pre-existing capabilities over vanilla SFT and likelihood-weighted baselines.

Efficiently fine-tunes patient-independent seizure detection models with tensor kernel machine.

problem Improving seizure detection accuracy for wearable devices.
method Transfer learning with tensor kernel machine using canonical polyadic decomposition.
result Patient fine-tuned model achieves high performance with smaller model size.

Study shows fine-tuned linear models outperform pretrained ones in transfer learning.

problem Transfer learning and fine-tuning in linear models for regression and binary classification.
method Stochastic gradient descent on pretrained linear models with small target data sets.
result Fine-tuned models outperform pretrained ones under certain conditions.

The paper identifies patterns in language model weights used for memorizing paragraphs.

problem Locating the specific mechanisms and weights used by language models to memorize paragraphs.
method Examined gradients and attention patterns in language models to identify memorized paragraphs.
result Gradients of memorized paragraphs have a distinguishable spatial pattern, and localized attention heads are involved in paragraph memorization.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.

GeLoRA optimizes LoRA fine-tuning by dynamically adjusting ranks based on intrinsic dimensionality.

problem Efficient fine-tuning of large language models with limited computational resources.
method GeLoRA computes intrinsic dimensionality to adaptively select LoRA ranks, balancing expressivity and efficiency.
result GeLoRA consistently outperforms recent baselines within the same parameter budget on multiple tasks.

New methods improve LLM preference optimization by intelligently weighting multiple reference models.

problem Improving LLM preference optimization with multiple reference models.
method Introducing four new weighting strategies for multiple-reference preference optimization.
result All four new weighting strategies outperform current methods on preference accuracy.

Fine-tunes deep neural networks to match theoretical bounds on generalization errors.

problem Improve generalization errors of deep neural networks by constraining weight norms.
method Proposes a two-stage renormalization procedure and a fine-grained SGD algorithm for training DNNs with constrained weights.
result Empirical generalization errors of DNNs are closer to theoretical bounds, improving accuracy.

LOFT separates subspace rotation and transformation for orthogonal fine-tuning.

problem Conflating subspace rotation and transformation in orthogonal fine-tuning.
method LOFT explicitly separates subspace rotation and transformation, using task-aware support selection.
result LOFT recovers principal-subspace orthogonal adaptation and improves efficiency-performance trade-off.

GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.

problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.

New mechanism protects neural network weights from privacy attacks during self-supervised learning.

problem Privacy risks during fine-tuning stage of self-supervised learning.
method Proposes a novel differential privacy mechanism using additive logistic noise.
result Reduces membership inference attack accuracy to 50% while maintaining below 5% performance loss.

New theory predicts deep neural networks can operate in an extended critical regime without fine-tuning.

problem Understanding the dynamics and computational principles of deep neural networks.
method Combining theories of heavy-tailed random matrices and non-equilibrium statistical physics.
result Deep neural networks can operate in an extended critical regime without fine-tuning parameters.

The condition number predicts efficient information encoding in neural units, aiding model fine-tuning.

problem Efficient information encoding in neural units for various tasks and input modalities.
method Linking the condition number to the log-volume scaling factor and entropy of the output distribution.
result High condition number indicates efficient encoding, reducing overall information transfer.

Paper analyzes fine-tuning methods for machine unlearning, proposing a new strategy to improve forgetting accuracy.

problem Improving fine-tuning methods to effectively forget specific subsets of data in machine learning models.
method Theoretical analysis and a novel Retention-Based Masking (RBM) strategy are proposed.
result RBM significantly improves unlearning accuracy while preserving retaining accuracy.

HiPPO-Prophecy models can learn dynamical systems without fine-tuning.

problem Learning dynamical systems in context without fine-tuning parameters.
method Introduced a novel weight construction for SSMs that approximates derivatives of input signals.
result Discrete SSMs can predict the next state of any dynamical system after observing previous states.

LoRA fine-tuning creates intruder dimensions that can cause forgetting, and a new law predicts when this happens.

problem Predicting when LoRA fine-tuning creates intruder dimensions that can cause catastrophic forgetting.
method Derived a per-layer critical update strength ss^\ast and an exact secular-equation characterization of the updated spectrum.
result The law localizes the empirical threshold within a factor of two on 82% of layers and separates intruder-bearing from intruder-free layers at deployment.

Deep neural network for cancer classification using autoencoders.

problem Cancer classification using molecular information.
method Using a Denoising Autoencoder (DAE) as weight initialization for a deep neural network, comparing two approaches: fixed weights and fine-tuning. Embedding strategies included encoding layers and complete autoencoder.
result Best F1 score of 98.04% for identifying thyroid cancer samples.